Experimental Realization of a Quantum Classification: Bell State Measurement Via Machine Learning

The Bell state is a crucial resource for the realization of quantum information tasks, and when combined with orbital angular momentum (OAM), it enables a high-dimensional Hilbert space, which is essential for high-capacity quantum communication. In this study, we demonstrate the recognition of OAM Bell states using interference patterns generated by a classical light source and a single-photon source from a Sagnac interferometer-based OAM Bell state evolution device. The interference patterns exhibit a one-to-one correspondence with the input Bell states, providing conclusive evidence for the full recognition of OAM Bell states. Furthermore, we introduce machine learning to the field of Bell state recognition by proposing a neural network model capable of accurately recognizing higher order single-photon OAM Bell states, even in the undersampling case. In particular, the model’s training set includes interference patterns of OAM Bell states generated by classical light sources, yet it is able to recognize single-photon OAM Bell states with high accuracy, without relying on quantum resources during training. Our innovative application of neural networks to the recognition of single-photon OAM Bell states not only circumvents the resource consumption and experimental difficulties associated with quantum light sources but also facilitates the study of OAM-based quantum information.